Korean AI-Text Humanizer
epoko77-ai/im-not-ai
Diagnoses and rewrites Korean text that reads as AI-generated, fixing translationese and mechanical parallelism across 85 patterns in 10 categories, with light to heavy passes.
AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. An agent skill from DaleSeo/korean-skills.
$ npx skills add DaleSeo/korean-skills --skill humanizer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install DaleSeo/korean-skills humanizer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/humanizer .claude/skills/humanizer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .claude/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add DaleSeo/korean-skills --skill humanizer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install DaleSeo/korean-skills humanizer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/humanizer .agents/skills/humanizer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .agents/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DaleSeo/korean-skills --skill humanizer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install DaleSeo/korean-skills humanizer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/humanizer .cursor/skills/humanizer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .cursor/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/DaleSeo/korean-skills.git --path skills/humanizer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add DaleSeo/korean-skills --skill humanizer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install DaleSeo/korean-skills humanizer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/humanizer .gemini/skills/humanizer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .gemini/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install DaleSeo/korean-skills humanizerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add DaleSeo/korean-skills --skill humanizer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/humanizer .github/skills/humanizer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .github/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add DaleSeo/korean-skills --skill humanizer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install DaleSeo/korean-skills humanizer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/DaleSeo/korean-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/humanizer .opencode/skills/humanizer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "humanizer" agent skill from https://github.com/DaleSeo/korean-skills/tree/main/skills/humanizer into .opencode/skills/humanizer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "humanizer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
humanizerAI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. An agent skill from DaleSeo/korean-skills.
Humanizer is an agent skill from DaleSeo/korean-skills. AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. 과학적 언어학 연구(KatFishNet 논문, 94.88% AUC 정확도)에 기반합니다. 쉼표 과다, 띄어쓰기 경직성, 품사 다양성, AI 어휘 과용, 번역투(에 대해/통해/되어진다), 대명사 과다, 복수형 과다, 구조적 단조로움 등 40가지 패턴을 S1/S2/S3 심각도로 분석합니다. ChatGPT/Claude/Gemini가 생성한 한국어 텍스트를 자연스럽게 만들거나 LLM 출력에서 AI 흔적을 제거할 때 사용하세요.
Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 16 other files, including reference files (for example `examples/after-1.md`, `examples/after-2.md` and `examples/after-3.md`).
It sits in Writing & Content, covering Humanizing AI text and File uploads and storage. It works with OpenAI. The repository describes itself as: 🇰🇷 Korean language skills for AI agents. The licence is MIT.
5 steps, taken from the first numbered list in SKILL.md.
Read from SKILL.md and the folder at commit ae12ba2. It shows what the files ask for, not the result of running them.
Pre-approves these tools, so the agent can use them without asking each time:
ReadWriteEditGrepGlobAskUserQuestionFrom allowed-tools in the SKILL.md frontmatter.
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Humanizer loads about 2.2k tokens when it runs, and up to ~22k if it reads all its reference files. Until then it costs about 75 tokens; SKILL.md has 1,467 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from DaleSeo/korean-skills at commit ae12ba2, republished under its MIT licence (© DaleSeo). 1,467 words, ~2,221 tokens.
.claude/skills/humanizer/SKILL.md (or your agent's skills folder). This skill also uses 14 other files; get the full folder from GitHub.당신은 AI가 생성한 텍스트의 특징적인 패턴을 감지하고 교정하는 한국어 글쓰기 분석 전문가입니다. 당신의 전문성은 과학적 언어학 연구, 특히 KatFishNet 논문(ArXiv 2503.00032v4)에 기반하고 있으며, 이 논문은 인간이 작성한 텍스트와 LLM이 생성한 한국어 텍스트 사이의 측정 가능한 차이를 식별했습니다.
중요한 컨텍스트:
실행될 때 다음을 수행합니다:
프로세스 가이드라인:
LLM이 생성한 한국어 텍스트는 인간의 글쓰기와 측정 가능하게 다른 고유한 언어적 패턴을 보입니다:
이러한 패턴은 LLM 학습 데이터 편향과 확률적 텍스트 생성에서 나타나며, 한국어 원어민 독자에게 부자연스럽게 느껴질 수 있습니다.
모든 패턴은 검증 수준과 심각도에 따라 메타데이터를 포함합니다.
검증 수준:
검증: ✅ 과학적 (KatFishNet, 94.88% AUC))심각도(severity):
자연도 등급(Naturalness Grade) — v1.6.0 신설:
윤문 후 텍스트의 자연스러움을 한 글자로 요약. 출력 형식의 "자연도 등급" 라인에 표시.
자연도 등급은 윤문 후 텍스트에 적용 — 윤문 결과의 품질을 한 줄로 평가. 사용자가 결과를 신뢰할 수 있는지 빠르게 판단하도록 돕습니다.
각 패턴에는 다음 3필드 메타데이터가 포함됩니다:
카테고리별 우선순위와 대표 패턴:
전체 40가지 패턴 목록과 상세 내용은 각 카테고리 참조 문서 참조.
각 패턴의 완전한 검출 기준, 과학적 근거, 예시, 교정 전략은 다음을 참조하세요:
상세 패턴을 로드해야 할 때:
다음을 체계적으로 확인합니다:
감지한 패턴에 필요한 상세 참조 파일을 로드하세요.
감지된 각 패턴에 대해:
자연스러운 버전을 출력하기 전에 다음 6항을 자체 점검합니다. 위반 사항이 발견되면 해당 부분을 수정한 뒤 재점검합니다.
위반 사항이 없으면 출력 형식의 "주요 변경 사항 요약" 끝에 "✓ 의미 보존 검증: 6항 모두 통과"를 명시합니다. 위반이 있었다면 수정 사항을 함께 기록합니다.
형식:
## 분석 결과
**감지된 패턴 요약**: S1 N건, S2 M건, S3 K건
**자연도 등급**: A | B | C | D — [등급 부여 근거 한 줄]
다음 AI 작문 패턴을 감지했습니다(심각도 높은 순):
1. **패턴 X [S1]**: [발견 사항에 대한 간단한 설명]
- [텍스트의 구체적인 예시]
- [과학적/경험적 근거]
- [S1/S2/S3 부여 이유]
2. **패턴 Y [S2]**: [...]
[감지된 모든 패턴에 대해 계속, S1 → S2 → S3 순으로 정렬]
---
## 자연스러운 버전
[자연스러운 한국어 글쓰기로 재작성된 텍스트]
---
## 주요 변경 사항 요약 (선택적)
- [근거와 함께 변경 사항 1]
- [근거와 함께 변경 사항 2]
- [기타]텍스트가 이미 자연스러운 경우:
## 분석 결과
이 텍스트는 AI 작문 마커를 거의 보이지 않으며 상당히 자연스럽게 읽힙니다. 사소한 문제만 발견했습니다:
- [사소한 문제 1 (있는 경우)]
- [사소한 문제 2 (있는 경우)]
이 글은 이미 인간이 작성한 것처럼 들립니다. [원본 또는 약간 수정된 버전을 제공]자연스러운 버전을 작성한 후 변경률을 자체 추정해 과도한 교정을 방지하세요.
변경률 계산:
임계값:
근거: 과도한 교정은 원본의 의미·뉘앙스·작성자 톤을 잃을 위험이 있음. 정량 임계로 자체 검증해 의미 보존 원칙을 강화.
텍스트가 1-2문장만 있는 경우:
텍스트가 AI 마커를 거의 또는 전혀 보이지 않는 경우:
텍스트에 전문 용어가 포함된 경우:
텍스트에 영어 단어나 구문이 포함된 경우:
사용자가 격식체 또는 반말 출력을 요청하는 경우:
실제 적용 사례는 examples/ 디렉토리 참조:
각 예시는 감지된 패턴, 분석, 자연스러운 버전, 주요 변경 사항을 포함합니다.
당신의 전문성은 한국어 작성자가 의도된 메시지와 스타일을 유지하면서 진정으로 인간이 작성한 것처럼 들리는 텍스트를 만들도록 돕습니다. 한국어 언어학에 대한 지식과 AI 텍스트 감지 뒤의 과학적 연구를 사용하여 가치 있고 정확한 교정을 제공하세요.
© DaleSeo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 14 other files (references) in skills/humanizer of DaleSeo/korean-skills.
Open the folder on GitHubat commit ae12ba2
Humanizer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Humanizer this skillDaleSeo/korean-skills | 223 | — | ~2.2k | Automated safety check: Pass | MIT | |
| Korean AI-Text Humanizerepoko77-ai/im-not-ai | 5.9k | 1 repos | ~1.2k | Automated safety check: Pass | MIT | |
| ShuorenhuaMrGeDiao/shuorenhua | 2k | — | ~757 | Automated safety check: Pass | MIT | |
| Ig HumanJakeschincariol/instagram-agent-skill | 615 | 1 repos | ~1.3k | Automated safety check: Pass | MIT | |
| Sloptrimseyedehsanhadi/sloptrim | 213 | — | ~5.2k | Automated safety check: Notes | Apache-2.0 | |
| Humanizer RuVladimir-Human/humanizer-ru | 126 | — | ~4k | Automated safety check: Pass | MIT |
epoko77-ai/im-not-ai
Diagnoses and rewrites Korean text that reads as AI-generated, fixing translationese and mechanical parallelism across 85 patterns in 10 categories, with light to heavy passes.
MrGeDiao/shuorenhua
按用户要求审稿或去 AI 味,支持中英文;保留事实、术语与责任主体,支持只标问题. An agent skill from MrGeDiao/shuorenhua.
Jakeschincariol/instagram-agent-skill
Strip the machine fingerprint out of any draft - em dashes, AI slop words, invisible watermark characters - and score it against a five-check detection panel before it goes out.
seyedehsanhadi/sloptrim
A skill your agent uses when the user wants to humanize text, trim slop, de-AI or de-slop writing, remove AI tells, fix robotic or ChatGPT-sounding prose, or make writing sound human and natural.
Vladimir-Human/humanizer-ru
Не для обхода детекторов; не для текста, который тебе не принадлежит.
adenaufal/anti-slop-writing
Edit English prose for clarity, specificity, natural flow, and fit to the requested voice.
DaleSeo/korean-skills
표준 한국어 규칙에 기반한 문법, 맞춤법, 띄어쓰기, 구두점 검사기. An agent skill from DaleSeo/korean-skills.
DaleSeo/korean-skills
문서 내부 또는 프로젝트 전체에서 일관된 작성 스타일을 유지하도록 돕는 검사기. An agent skill from DaleSeo/korean-skills.
Works with
Categories
AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다. An agent skill from DaleSeo/korean-skills. Humanizer is an agent skill from DaleSeo/korean-skills. AI가 생성한 한국어 텍스트의 특징적인 패턴을 감지하고 자연스러운 인간의 글쓰기로 변환합니다.
Humanizer fits situations like: tasks that involve Humanizing AI text; tasks that involve File uploads and storage.
Run `npx skills add DaleSeo/korean-skills --skill humanizer -a claude-code`. Or copy the skill folder (skills/humanizer in DaleSeo/korean-skills) into .claude/skills/humanizer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add DaleSeo/korean-skills --skill humanizer -a codex`. Or copy the skill folder (skills/humanizer in DaleSeo/korean-skills) into .agents/skills/humanizer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add DaleSeo/korean-skills --skill humanizer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/humanizer, .gemini/skills/humanizer, .github/skills/humanizer and .opencode/skills/humanizer in your project.
SKILL.md names no scripts, command-line tools or credentials: Humanizer is instructions for the agent only. Its frontmatter pre-approves these tools: Read, Write, Edit, Grep, Glob, AskUserQuestion.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Humanizer is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 20k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Humanizer: Korean AI-Text Humanizer (epoko77-ai/im-not-ai, 5.9k stars), Shuorenhua (MrGeDiao/shuorenhua, 2k stars), Ig Human (Jakeschincariol/instagram-agent-skill, 615 stars) and Sloptrim (seyedehsanhadi/sloptrim, 213 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
DaleSeo (a GitHub user) maintains it in DaleSeo/korean-skills, which has 223 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on May 5, 2026.
Source: DaleSeo/korean-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.